Bristlecone Logic Utilities

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the full burden. It discloses the core behaviors (forward resolution, IPv4/IPv6) and the safety intent (SSRF prevention), which implies a safe read-only operation. However, 'network routing verification' is somewhat vague, leaving some ambiguity about what exactly is verified. This is a minor gap given that it clearly indicates the operational scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no filler: a clear action statement, a usage recommendation, and an explicit exclusion. The most critical information (what it does) is front-loaded, and every sentence serves a distinct purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with no output schema, the description covers purpose, usage, and exclusions. It does not describe the return format or error behavior, but given the simplicity and the safety-focused use case, this is a minor omission. The description is sufficiently complete for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents the 'domain' parameter. The description adds extra value by explicitly instructing not to include protocols or URL paths and emphasizing the FQDN format. This goes beyond the schema's basic type and format, improving the agent's chance of correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Performs forward DNS resolution and network routing verification' and specifies it resolves IPv4 and IPv6 addresses. It also names the exact use case (SSRF guard) and explicitly differentiates from WHOIS and port scanning, making it distinguishable from any related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance on when to use it ('Use to verify host reachability and guard autonomous agents against SSRF before making HTTP requests') and when not to ('Do not use for WHOIS domain registration lookups or deep port scanning'). This is exemplary usage instruction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It discloses the transformation behavior and the return shape ('Returns an array of formatted text chunks'), which is adequate for a pure transform tool. However, it does not describe edge-case behavior (e.g., text shorter than chunk_size, how boundary chunking is resolved, or determinism). The disclosure is correct but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with zero filler. The core partitioning behavior is front-loaded, the return type is stated, and usage guidance is appended efficiently. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complexity is low: 3 flat, fully-covered parameters, no output schema, no nested objects. The description covers purpose, use case, exclusions, and return shape. The only minor gap is absence of edge-case behavior notes (e.g., handling of text shorter than the chunk size), which is a small omission given the low complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema documents all three parameters including defaults and constraints (chunk_size default 500/min 50; chunk_overlap default 50/min 0). The description's 'configurable character overlap' merely echoes the schema. With full schema coverage, baseline 3 applies; the description adds little parameter meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Partitions raw text documents into uniform sliding-window segments with configurable character overlap.' It also discloses the return type ('Returns an array of formatted text chunks'). None of the siblings (audit_dns, eval_expression, extract_web, repair_json, validate_schema) perform chunking, so there is no ambiguity about which tool this is.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use ('preparing unstructured documents for vector database embeddings and RAG retrieval pipelines') and explicit when-not-to-use ('Do not use for syntactic token counting or semantic sentence segmentation'). This is better than merely naming an alternative; it states the exclusions directly, leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. It discloses the critical safety traits: deterministic evaluation, AST isolation, and strict blocking of arbitrary code execution. It stops short of stating error behavior for invalid expressions, return format, or numeric precision, which would make it fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero filler. The core purpose is front-loaded, followed immediately by the use/don't-use guidance. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with full schema coverage and no output schema, the description covers purpose, safety behavior, and usage exclusions concisely. The only genuine gaps are return format and error handling for malformed expressions, which are not disclosed anywhere.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents the expression parameter with an example. The description adds value by constraining what counts as a valid expression (arithmetic/mathematical/boolean only) and explicitly excluding arbitrary Python statements, which sharpens the parameter's intended scope beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('evaluates') and a well-defined resource ('arithmetic, mathematical, and logical expressions'), plus the AST-isolated sandbox context. The stated purpose of preventing LLM calculation errors and blocking arbitrary code execution makes it unmistakably distinct from the unrelated siblings (audit_dns, chunk_text, extract_web, repair_json, validate_schema).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly directs when to use ('reliable numerical calculations and boolean logic') and, in the next sentence, when not to ('Do not use for executing arbitrary Python statements or importing external libraries'). This is a clear inclusion/exclusion pair with no ambiguity left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for behavioral disclosure. It reveals that the tool strips HTML tags, navigation bars, and scripts, returns clean body text and HTTP status code, and implies it only handles public pages. It does not mention timeouts, redirects, or non-HTML handling, but covers the core behavior well. This is above average but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact (three sentences) and front-loads the core function, then its output, then usage constraints. Every sentence serves a purpose with zero fluff. It is efficiently structured for quick agent comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (single parameter, no output schema), the description is complete: it explains what the tool returns (body text and status code), when to use it, and when not to. An agent receives all necessary information to invoke it correctly without needing additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the single 'url' parameter has a detailed description including protocol and example). The tool description adds only the mention of 'HTTP or HTTPS' and 'public,' which is already implied by the schema's format uri and description. At 100% coverage, the baseline of 3 applies, and the description adds no significant extra meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Fetches and sanitizes'), the resource ('readable text content from any public HTTP or HTTPS web page'), and the scope ('any public...'). It explicitly differentiates from sibling tools (audit_dns, chunk_text, etc.) by describing a unique web-fetching function, leaving no ambiguity about what it does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit when-to-use guidance ('Use when an agent needs primary webpage content for summarization or analysis') and clear exclusions ('Do not use for authenticated pages or executing JavaScript'). This directly helps an agent decide between this and alternatives, even though siblings are unrelated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must carry the behavioral disclosure. It states the deterministic nature, the kinds of repairs performed, and the return type ('Returns parsed valid JSON object'). It does not cover error behavior or edge cases, but for a repair tool that guarantees a parsed object, this is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and efficient, with the core purpose front-loaded. Every sentence adds value: the repair scope, the specific error types, the return type, and usage restrictions. There is no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description covers the essential information an agent needs: what it does, when to use it, and what it returns. It could mention how it handles unresolvable JSON or whether it throws errors, but for the expected use case it is adequately complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already has a 100%-coverage description of the single parameter (raw_json) explaining its role as malformed JSON text needing repair. The tool description adds no additional parameter-level details, so the baseline of 3 applies—schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the exact action ('parses and repairs'), the specific resource ('malformed, truncated, or unclosed JSON strings'), and the context (produced by LLMs). It clearly differentiates from siblings by focusing on repair rather than validation or extraction, and names concrete error types (missing brackets, unescaped quotes, trailing commas) that make the purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use ('when an LLM produces syntax-broken JSON') and clear exclusions ('do not use on valid non-JSON prose or for modifying data values'). It does not name an alternative sibling directly, but the context is sufficient for an agent to decide when this tool applies versus others.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the deterministic nature ('Deterministically validates'), describes the return (a boolean status and a list of missing keys), and explicitly delimits what it does not do (regex validation, deep recursive casting), which prevents incorrect assumptions. It doesn't mention side effects, but validation implies non-mutating behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The purpose is stated first, followed directly by usage guidance and exclusions. Every word carries weight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with two required parameters, no output schema, and no similar siblings, the description covers the essential context: what it validates, how it returns results, and its limitations. It could mention error handling, but that's not required for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already covers both parameters with descriptions and an example, so the description adds little beyond labeling it a 'reference schema dictionary'. With 100% schema coverage, the baseline is 3, and this description does not meaningfully augment the schema's clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (validates), a resource (target JSON payload), and the precise scope (contains all mandatory keys from a reference schema dictionary). It distinguishes itself from other tools by explicitly saying it is not for regex string validation or deep recursive type casting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit guidance on when to use ('Use when verifying payload structure before downstream processing') and states clear exclusions ('Do not use for regex string validation or deep recursive type casting'). While it doesn't name a specific sibling alternative, it gives enough context to avoid misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.